Jingrui Pang
2 papers · Latest:
Robotics
MotuBrain: An Advanced World Action Model for Robot Control
MotuBrain is a unified multimodal generative model for robot control, jointly modeling video and action with a UniDiffuser architecture.
2604.27792
Computer VisionXEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
XEmbodied is a foundation model that enhances VLMs with intrinsic 3D geometric and physical awareness for robust performance in embodied environments.
2604.18484
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.